Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Mohammad Norouzi

SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network


Apr 05, 2021
William Chan, Daniel Park, Chris Lee, Yu Zhang, Quoc Le, Mohammad Norouzi

* submitted to INTERSPEECH 

  Access Paper or Ask Questions

Benchmarks for Deep Off-Policy Evaluation


Mar 30, 2021
Justin Fu, Mohammad Norouzi, Ofir Nachum, George Tucker, Ziyu Wang, Alexander Novikov, Mengjiao Yang, Michael R. Zhang, Yutian Chen, Aviral Kumar, Cosmin Paduraru, Sergey Levine, Tom Le Paine

* ICLR 2021 paper. Policies and evaluation code are available at https://github.com/google-research/deep_ope 

  Access Paper or Ask Questions

Big Self-Supervised Models Advance Medical Image Classification


Jan 13, 2021
Shekoofeh Azizi, Basil Mustafa, Fiona Ryan, Zachary Beaver, Jan Freyberg, Jonathan Deaton, Aaron Loh, Alan Karthikesalingam, Simon Kornblith, Ting Chen, Vivek Natarajan, Mohammad Norouzi


  Access Paper or Ask Questions

What's in a Loss Function for Image Classification?


Oct 30, 2020
Simon Kornblith, Honglak Lee, Ting Chen, Mohammad Norouzi


  Access Paper or Ask Questions

No MCMC for me: Amortized sampling for fast and stable training of energy-based models


Oct 14, 2020
Will Grathwohl, Jacob Kelly, Milad Hashemi, Mohammad Norouzi, Kevin Swersky, David Duvenaud


  Access Paper or Ask Questions

Mastering Atari with Discrete World Models


Oct 05, 2020
Danijar Hafner, Timothy Lillicrap, Mohammad Norouzi, Jimmy Ba

* 8 pages, 4 figures, 4 tables 

  Access Paper or Ask Questions

WaveGrad: Estimating Gradients for Waveform Generation


Sep 02, 2020
Nanxin Chen, Yu Zhang, Heiga Zen, Ron J. Weiss, Mohammad Norouzi, William Chan


  Access Paper or Ask Questions

RL Unplugged: Benchmarks for Offline Reinforcement Learning


Jul 02, 2020
Caglar Gulcehre, Ziyu Wang, Alexander Novikov, Tom Le Paine, Sergio Gomez Colmenarejo, Konrad Zolna, Rishabh Agarwal, Josh Merel, Daniel Mankowitz, Cosmin Paduraru, Gabriel Dulac-Arnold, Jerry Li, Mohammad Norouzi, Matt Hoffman, Ofir Nachum, George Tucker, Nicolas Heess, Nando de Freitas

* 21 pages including supplementary material, the github link for the datasets: https://github.com/deepmind/deepmind-research/rl_unplugged 

  Access Paper or Ask Questions

Big Self-Supervised Models are Strong Semi-Supervised Learners


Jun 17, 2020
Ting Chen, Simon Kornblith, Kevin Swersky, Mohammad Norouzi, Geoffrey Hinton

* code and pretrained models at https://github.com/google-research/simclr 

  Access Paper or Ask Questions

Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation


May 03, 2020
Xuanli He, Gholamreza Haffari, Mohammad Norouzi

* accepted to ACL2020 

  Access Paper or Ask Questions

Non-Autoregressive Machine Translation with Latent Alignments


Apr 22, 2020
Chitwan Saharia, William Chan, Saurabh Saxena, Mohammad Norouzi


  Access Paper or Ask Questions

Exemplar VAEs for Exemplar based Generation and Data Augmentation


Apr 09, 2020
Sajad Norouzi, David J. Fleet, Mohammad Norouzi


  Access Paper or Ask Questions

NiLBS: Neural Inverse Linear Blend Skinning


Apr 06, 2020
Timothy Jeruzalski, David I. W. Levin, Alec Jacobson, Paul Lalonde, Mohammad Norouzi, Andrea Tagliasacchi


  Access Paper or Ask Questions

SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models


Apr 01, 2020
Yucen Luo, Alex Beatson, Mohammad Norouzi, Jun Zhu, David Duvenaud, Ryan P. Adams, Ricky T. Q. Chen

* ICLR 2020 

  Access Paper or Ask Questions

Imputer: Sequence Modelling via Imputation and Dynamic Programming


Feb 20, 2020
William Chan, Chitwan Saharia, Geoffrey Hinton, Mohammad Norouzi, Navdeep Jaitly

* preprint 

  Access Paper or Ask Questions

A Simple Framework for Contrastive Learning of Visual Representations


Feb 13, 2020
Ting Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey Hinton


  Access Paper or Ask Questions

Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One


Dec 11, 2019
Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Mohammad Norouzi, Kevin Swersky


  Access Paper or Ask Questions

NASA: Neural Articulated Shape Approximation


Dec 06, 2019
Timothy Jeruzalski, Boyang Deng, Mohammad Norouzi, JP Lewis, Geoffrey Hinton, Andrea Tagliasacchi


  Access Paper or Ask Questions

Dream to Control: Learning Behaviors by Latent Imagination


Dec 03, 2019
Danijar Hafner, Timothy Lillicrap, Jimmy Ba, Mohammad Norouzi

* 9 pages, 12 figures 

  Access Paper or Ask Questions

Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse


Nov 06, 2019
James Lucas, George Tucker, Roger Grosse, Mohammad Norouzi

* 11 main pages, 10 appendix pages. 13 figures total. Accepted at 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) 

  Access Paper or Ask Questions

Efficient Exploration with Self-Imitation Learning via Trajectory-Conditioned Policy


Jul 24, 2019
Yijie Guo, Jongwook Choi, Marcin Moczulski, Samy Bengio, Mohammad Norouzi, Honglak Lee


  Access Paper or Ask Questions

Striving for Simplicity in Off-policy Deep Reinforcement Learning


Jul 10, 2019
Rishabh Agarwal, Dale Schuurmans, Mohammad Norouzi


  Access Paper or Ask Questions

Similarity of Neural Network Representations Revisited


May 14, 2019
Simon Kornblith, Mohammad Norouzi, Honglak Lee, Geoffrey Hinton

* Accepted to ICML 2019 

  Access Paper or Ask Questions

Learning to Generalize from Sparse and Underspecified Rewards


Feb 19, 2019
Rishabh Agarwal, Chen Liang, Dale Schuurmans, Mohammad Norouzi


  Access Paper or Ask Questions

Understanding the impact of entropy on policy optimization


Nov 29, 2018
Zafarali Ahmed, Nicolas Le Roux, Mohammad Norouzi, Dale Schuurmans


  Access Paper or Ask Questions

Contingency-Aware Exploration in Reinforcement Learning


Nov 05, 2018
Jongwook Choi, Yijie Guo, Marcin Moczulski, Junhyuk Oh, Neal Wu, Mohammad Norouzi, Honglak Lee

* Preprint, work in progress. Under review at ICLR 2019 

  Access Paper or Ask Questions